Add credit transaction totals to daily stats

[gianpaj]

Summary

• fetch credit transaction descriptions in the daily stats cron route
• parse dollar amounts and include totals in Telegram message

Testing

• pnpm run lint:write
• pnpm run format
• pnpm run type-check (fails: Cannot find module 'contentlayer/generated')
• pnpm run check-translations

---

https://chatgpt.com/codex/tasks/task_e_688346ee1f3c832c9eadfd1143967e02

[vercel]

The latest updates on your projects. Learn more about Vercel for Git ↗︎

Name	Status	Preview	Comments	Updated (UTC)
sexyvoice	✅ Ready (Inspect)	Visit Preview	💬 Add feedback	Jul 28, 2025 11:26am

[bolt-new-by-stackblitz]

Run & review this pull request in StackBlitz Codeflow.

[jazzberry-ai]

This repository is associated with gianpaj whose free trial has ended. Subscribe at jazzberry.ai.
_{If this is an error contact us at [email protected].}

[gemini-code-assist]

Summary of Changes

Hello @gianpaj, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

I've updated the daily stats cron route to include the total monetary value of credit transactions. This enhancement fetches transaction descriptions, parses the dollar amounts from them, and then incorporates these daily and weekly totals into the Telegram message, providing a more comprehensive financial overview.

Highlights

• Feature Enhancement: I've added the capability to calculate and display the total dollar amounts from credit transactions for both the previous day and the last seven days within the daily stats report.
• Data Fetching: I've modified the Supabase queries in the daily stats API route to specifically retrieve the 'description' field from 'credit_transactions' for both daily and weekly periods.
• Data Processing: I've implemented a new utility function, 'extractDollarAmount', which uses regular expressions to accurately parse and extract monetary values from the transaction description strings.
• Reporting: I've updated the Telegram message format to include the newly calculated daily and weekly credit transaction dollar totals, alongside the existing transaction counts.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point in your pull request via creating an issue comment (i.e. comment on the pull request page) using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in issue comments and review comments.
Help	/gemini help	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments or fill out our survey to provide feedback.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[gemini-code-assist]

Code Review

This pull request adds logic to calculate and report the total dollar amount of credit transactions in the daily stats message. I've identified an opportunity to improve performance by consolidating database queries. I've also suggested improvements to the amount-parsing function for better robustness and readability, and added fallbacks to avoid NaN values.

[gemini-code-assist]

There are two separate database queries to get the weekly credit transaction count (lines 149-153) and the descriptions (this block). These can be combined into a single, more efficient query. This would reduce the number of round-trips to the database.

You could replace lines 154-159 with a single query like this:

const { data: creditsWeekData } = await supabase
  .from('credit_transactions')
  .select('description')
  .in('type', ['purchase', 'topup'])
  .gte('created_at', sevenDaysAgo.toISOString())
  .lt('created_at', today.toISOString());

A similar optimization can be applied to the daily credit queries on lines 118-123.

[gemini-code-assist]

The regex /\$([\d.]+)/ is a bit too permissive and could match an invalid number like $1.2.3. Using /\$(\d+(?:\.\d+)?)/ would be more precise. Adding some more structure and optional chaining can make the function's logic clearer and safer.

function extractDollarAmount(description: string): number {
  // Matches formats like "$12.34"
  const dollarMatch = description.match(/\$(\d+(?:\.\d+)?)/);
  if (dollarMatch?.[1]) {
    return Number.parseFloat(dollarMatch[1]);
  }

  // Matches formats like "12.34 USD"
  const usdMatch = description.match(/^(\d+(?:\.\d+)?)\s*USD/);
  if (usdMatch?.[1]) {
    return Number.parseFloat(usdMatch[1]);
  }

  return 0;
}

[gemini-code-assist]

Consider adding a fallback to 0 if creditsTodayAmount is null or undefined to avoid potential NaN values in the Telegram message.

`Credit Transactions: ${creditsTodayCount} (${formatChange(creditsTodayCount, creditsPrevCount)}) - $${(creditsTodayAmount || 0).toFixed(2)} ${creditsTodayCount > 0 ? '🤑' : '😿'}`

[gemini-code-assist]

Consider adding a fallback to 0 if creditsWeekAmount is null or undefined to avoid potential NaN values in the Telegram message.

`  - 7d total ${creditsWeekCount}, avg ${(creditsWeekCount / 7).toFixed(1)} ($${(creditsWeekAmount || 0).toFixed(2)})`